Y. A. Pachepsky, D. Timlin, and . G. Varallyay, Artificial neural networks to estimate soil 473 water retention from easily measurable data, Soil Science Society of America Journal, vol.60, pp.474-727, 1996.
DOI : 10.2136/sssaj1996.03615995006000030007x

Y. A. Pachepsky and W. J. Rawls, Accuracy and Reliability of Pedotransfer Functions as Affected by Grouping Soils, Soil Science Society of America Journal, vol.63, issue.6, pp.1748-1757, 1999.
DOI : 10.2136/sssaj1999.6361748x

Y. A. Pachepsky, W. J. Rawls, and H. S. Lin, Hydropedology and pedotransfer functions, Geoderma, vol.131, issue.3-4, p.478, 2006.
DOI : 10.1016/j.geoderma.2005.03.012

, Geoderma, vol.131, pp.308-316

N. G. Patil, D. K. Pal, C. Mandal, and D. K. Mandal, Soil water retention characteristics 480 of vertisols and pedotransfer functions based on nearest neighbor and neural networks 481 approaches to estimate AWC, Journal of Irrigation and Drainage Engineering, vol.138, issue.2, pp.482-177, 2012.

T. B. Ramos, M. C. Goncalves, D. Brito, J. C. Martins, and L. S. Pereira, Development of class pedotransfer functions for integrating water retention properties into Portuguese soil maps, Soil Research, vol.51, issue.4, pp.262-277, 2013.
DOI : 10.1071/SR12347

J. M. Reichert, J. A. Albuquerque, A. R. Kaiser, D. J. Reinert, F. L. Urach et al., Estimation of water retention and availability in soils of Rio Rrande Do Sul, Revista, vol.487, issue.488, 2009.

, Brasileira de Ciência do Solo, vol.33, pp.1547-1560

J. Rigot, évolution ralentie du milieu naturel dans la steppe aride du nord de la 490, 2006.

. Syrie-À-l-'holocène, Géomorphologie: Relief, pp.259-274

M. Robert and D. Tessier, Méthode de préparation des argiles des sols pour les études 492 minéralogiques, Annales Agronomiques, vol.25, pp.859-882, 1974.

P. Santra and B. S. Das, Pedotransfer functions for soil hydraulic properties developed from a hilly watershed of Eastern India, Geoderma, vol.146, issue.3-4, pp.439-448, 2008.
DOI : 10.1016/j.geoderma.2008.06.019

M. G. Schaap, F. J. Leij, and T. M. Van-genuchten, rosetta : a computer program for estimating soil hydraulic parameters with hierarchical pedotransfer functions, Journal of Hydrology, vol.251, issue.3-4, p.497, 2001.
DOI : 10.1016/S0022-1694(01)00466-8

. Hydrology, , pp.163-176

M. G. Schaap and W. Bouten, Modeling water retention curves of sandy soils using neural networks, Water Resources Research, vol.66, issue.10, pp.3033-3040, 1996.
DOI : 10.1016/0016-7061(94)00079-P

M. G. Schaap and W. J. Pachepsky, Accuracy and uncertainty in PTF predictions, 2004.
DOI : 10.1016/S0166-2481(04)30003-6

. Rawls, Development of Pedotransfer Functions in Soil Hydrology, p.502

, Soil Science, vol.30, pp.33-43

M. G. Schaap, F. J. Leij, M. Van-genuchten, and . Th, rosetta : a computer program for estimating soil hydraulic parameters with hierarchical pedotransfer functions, Journal of Hydrology, vol.251, issue.3-4, p.505, 2001.
DOI : 10.1016/S0022-1694(01)00466-8

. Hydrology, , pp.163-176

R. Sommer, C. Piggin, A. Haddad, A. Hajdibo, P. Hayek et al., Simulating the effects of zero tillage and crop residue retention on water relations and yield of wheat under rainfed semiarid Mediterranean conditions, Field Crops Research, vol.132, pp.40-52, 2012.
DOI : 10.1016/j.fcr.2012.02.024

S. Touil, A. Degré, and M. N. Chabaka, Transposability of pedotransfer functions for 510 estimating water retention of Algerian soils, Desalination and Water Treatment, vol.57, pp.12-511, 2016.

J. Tomasella, Y. A. Pachepsky, S. Crestana, and J. Rawls, , p.513, 2003.

, Techniques to Develop Pedotransfer Functions for Water Retention, Soil Science Society, p.514

, America Journal, vol.67, pp.1085-1092

N. K. Twarakavi, J. Simonek, and M. Schaap, Development of pedotransfer 516 functions for estimation of soil hydraulic parameters using support vector machines, 2009.

, Science Society of America Journal, vol.73, pp.1443-1452

H. Vereecken, J. Maes, J. Feyen, and P. Darius, Estimating the soil moisture retention, 1989.

, Figure 1: The typical topologies of the continuous and class-PTFs used in this study. (a): continuous-PTFs 600 providing the parameters of the van Genuchten model (1980), (b): continuous-PTFs providing the water content 601 at several matric potentials, (c): class-PTFs providing the parameters of the van Genuchten model, ): 602 class-PTFs providing the water content at several matric potentials, and (e): artificial neural networks, 1980.

. Ptfs, 2 : volumetric water content in cm 3 cm -3 at seven different matric potentials, ? r , ? s , ? and n are 604 the parameters of the van Genuchten equation, T: texture, BD: bulk density, OC: organic carbon, H: type of 605 horizon